wiki-architect
Pass
Audited by Gen Agent Trust Hub on Aug 16, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted repository files to generate structured documentation and prompts.
- Ingestion points: The agent scans the repository file tree and README content as specified in the procedure.
- Boundary markers: The instructions do not include markers or delimiters to differentiate between trusted documentation logic and potentially malicious instructions embedded within the analyzed source code.
- Capability inventory: The skill is designed to generate hierarchical JSON catalogues containing titles and prompts; it does not explicitly invoke high-risk command execution or network operations, though the agent's general environment may have such tools.
- Sanitization: There is no evidence of content validation, escaping, or filtering for ingested codebase data before it is interpolated into the generated output.
Audit Metadata